Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2576 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1944866 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1617292 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1915295 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1414926 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1575895 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1273540 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1990092 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5652. Min Act: -0.0000

Data Index: 364527 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1911526 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5168. Min Act: -0.0000

Data Index: 996435 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5077. Min Act: -0.0000

Data Index: 115030 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.4895. Min Act: -0.0000

Data Index: 895469 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1157303 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1876987 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1752677 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.4951. Min Act: -0.0000

Data Index: 757330 (The Pile)

Max Activating Token Index: 359

Text #16

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.4724. Min Act: -0.0000

Data Index: 592927 (The Pile)

Max Activating Token Index: 280

Text #17

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.4777. Min Act: -0.0000

Data Index: 521129 (The Pile)

Max Activating Token Index: 239

Text #18

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.4777. Min Act: -0.0000

Data Index: 321282 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.4574. Min Act: -0.0000

Data Index: 876985 (The Pile)

Max Activating Token Index: 641